Running multiple harnesses at once is the key agent skill: Claude Code, Codex, Fable, DeepSeek combo
EXM7777 · x · 2026-09-18
The author argues the most important skill in agent work right now is running multiple harnesses in parallel — one harness with its own subagents isn't enough. His example combo: send plans from Claude Code to Codex and GPT-6 Astra for review, route writing to Fable (which he finds clearly better than GPT models), and offload bulk background tasks to DeepSeek for its dirt-cheap cost. Finding the best harness-plus-model pairing per task takes reps, but yields a step-change in speed and quality.
More from coding & agent
- Paying a FasTrak toll invoice automatically with a Grok bot and Link — jeff_weinstein · 2026-09-18
- Honeycomb CTO on AI slop: half the company hates it, half hates the holdouts — mipsytipsy · 2026-09-18
- Credential-free MCP server template lets agents call tools without touching API keys — uzi24- · 2026-09-18
- Claude Handles 80% of My Sales Workflow — But It Can't Close the Loop — Prestigious_Rub5 · 2026-09-18
- Dev loses a day of benchmarks to Claude Opus 5, begs for Opus 4.5 back — julianharris · 2026-09-18
- Why only foundational model labs can self-improve with scaffolds, and why OpenAI/Anthropic likely already do — menhguin · 2026-09-18